paper-with-me

홈 › Papers

Bringing a Personal Point of View: Evaluating Dynamic 3D Gaussian Splatting for Egocentric Scene Reconstruction

2026-04-26 · Jan Warchocki, Xi Wang, Jonas Kulhanek, Jan van Gemert arxiv

Egocentric video provides a unique view into human perception and interaction, with growing relevance for augmented reality, robotics, and assistive technologies. However, rapid camera motion and complex scene dynamics pose major challenges for 3D reconstruction from this perspective. While 3D Gaussian Splatting (3DGS) has become a state-of-the-art method for efficient, high-quality novel view synthesis, variants, that focus on reconstructing dynamic scenes from monocular video are rarely evaluated on egocentric video. It remains unclear whether existing models generalize to this setting or if egocentric-specific solutions are needed. In this work, we evaluate dynamic monocular 3DGS models on egocentric and exocentric video using paired ego-exo recordings from the EgoExo4D dataset. We find that reconstruction quality is consistently lower in egocentric views. Analysis reveals that the difference in reconstruction quality, measured in peak signal-to-noise ratio, stems from the reconstruction of static, not dynamic, content. Our findings underscore current limitations and motivate the development of egocentric-specific approaches, while also highlighting the value of separately evaluating static and dynamic regions of a video.

📄 PDF Abstract BibTeX arXiv:2604.23803

Code (0)

등록된 구현이 없습니다.

Tasks

Novel View Synthesis3D Reconstruction

Similar Papers 제목 키워드 기반

Human Centered NLP with User-Factor Adaptation

2017-09-01 · EMNLP 2017 9 · Veronica Lynn, Youngseo Son, Vivek Kulkarni, Niranjan Balasubramanian 외

We pose the general task of user-factor adaptation {--} adapting supervised learning models to real-valued user factors inferred from a background of their language, reflecting the idea that a piece of text should be und…

Document ClassificationDomain AdaptationPOSPOS Tagging+3

SAC: A Framework for Measuring and Inducing Personality Traits in LLMs with Dynamic Intensity Control

2025-06-26 · Adithya Chittem, Aishna Shrivastava, Sai Tarun Pendela, Jagat Sesh Challa 외

Large language models (LLMs) have gained significant traction across a wide range of fields in recent years. There is also a growing expectation for them to display human-like personalities during interactions. To meet t…

Attribute

Bringing Telepresence to Every Desk

2023-04-03 · Shengze Wang, Ziheng Wang, Ryan Schmelzle, Liujie Zheng 외

In this paper, we work to bring telepresence to every desktop. Unlike commercial systems, personal 3D video conferencing systems must render high-quality videos while remaining financially and computationally viable for …

Reconstructing Objects in-the-wild for Realistic Sensor Simulation

2023-11-09 · Ze Yang, Sivabalan Manivasagam, Yun Chen, Jingkang Wang 외

Reconstructing objects from real world data and rendering them at novel views is critical to bringing realism, diversity and scale to simulation for robotics training and testing. In this work, we present NeuSim, a novel…

Diversity

RAG-Optimized Tibetan Tourism LLMs: Enhancing Accuracy and Personalization

2024-08-21 · Jinhu Qi, Shuai Yan, Yibo Zhang, Wentao Zhang 외

With the development of the modern social economy, tourism has become an important way to meet people's spiritual needs, bringing development opportunities to the tourism industry. However, existing large language models…

HallucinationRAGRetrievalRetrieval-augmented Generation